Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Vision-Intensive Perception on MME-Unify
Loading...
13
Spot Difference
Qwen2.5-VL-7B-Instruct
12.32
16.91
21.5
26.09
Jan 31, 2026
Spot Difference
Auxiliary Lines
Average Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Spot Difference
Auxiliary Lines
Average Score
Qwen2.5-VL-7B-Instruct
Model Scale=7B
2026.01
13
32.7
48.8
R1-onevision-RL
Training Paradigm=RL
2026.01
14
30.8
54.2
MM-EurekaQwen-7B
Model Scale=7B
2026.01
19
44.2
42.4
Thyme
2026.01
21
46.2
57.2
LLaVA-OneVision-Qwen2-7B
Model Scale=7B
2026.01
27
46.2
50
Ours (SFT)
Training Paradigm=SFT
2026.01
27
34.6
55.2
Ours (RL)
Training Paradigm=RL
2026.01
28
38.5
55.1
Janus-Pro-7B
Model Scale=7B
2026.01
29
28.8
-
InternVL2.5-8B
Model Scale=8B
2026.01
30
32.7
49.6
Feedback
Search any
task
Search any
task